{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:48:15Z","timestamp":1793206095922,"version":"4.5.0"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01457","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15703-15713","source":"Crossref","is-referenced-by-count":4,"title":["Tread: Token Routing for Efficient Architecture-Agnostic Diffusion Training"],"prefix":"10.1109","author":[{"given":"Felix","family":"Krause","sequence":"first","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timy","family":"Phan","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Gui","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan Andreas","family":"Baumann","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich, Munich Center for Machine Learning (MCML)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2023","journal-title":"In ICLR"},{"key":"ref2","author":"Alkin","year":"2024","journal-title":"Vision-lstm: xlstm as generic vision backbone"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01235"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref8","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3228915"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref12","author":"Fei","year":"2024","journal-title":"Scalable diffusion models with state space backbone"},{"key":"ref13","article-title":"Scaling diffusion transformers to 16 billion parameters","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Diffusion-rwkv: Scaling rwkvlike architectures for diffusion models","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Modelagnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"In ICML"},{"key":"ref16","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref19","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024","journal-title":"COLM"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref21","author":"Gupta","year":"2022","journal-title":"Maskvit: Masked visual pre-training for video prediction"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","article-title":"What matters in transformers? not all attention is needed","author":"He","year":"2024","journal-title":"CoRRd, abs\/2406.15786"},{"key":"ref25","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"In NeurIPS"},{"key":"ref26","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"In NeurIPS"},{"issue":"2","key":"ref27","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27998"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01766"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref32","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"In NeurIPS"},{"key":"ref33","article-title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","author":"Kynk\u00e4\u00e4nniemi","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref35","author":"Liang","year":"2024","journal-title":"Scaling laws for diffusion transformers"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"In ICLR"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"In ICLR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref41","author":"Ma","year":"2023","journal-title":"Deepcache: Accelerating diffusion models for free"},{"key":"ref42","author":"Ma","year":"2024","journal-title":"Learning-to-cache: Accelerating diffusion transformer via layer caching"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref44","author":"Mei","year":"2023","journal-title":"Deep networks as denoising algorithms: Sample-efficient learning of diffusion models in high-dimensional graphical models"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref46","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_27"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"ref50","author":"Pi\u00f3ro","year":"2024","journal-title":"Moe-mamba: Efficient selective state space models with mixture of experts"},{"key":"ref51","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Poole","year":"2023"},{"key":"ref52","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume-title":"In Advances in Neural Information Processing Systems","author":"Rao","year":"2021"},{"key":"ref53","article-title":"Mixture-ofdepths: Dynamically allocating compute in transformer-based language models","author":"Raposo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref57","article-title":"Assessing generative models via precision and recall","volume":"31","author":"Sajjadi","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref58","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_19"},{"key":"ref60","author":"Shazeer","year":"2017","journal-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer"},{"key":"ref61","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"In ICML"},{"key":"ref62","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref63","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref64","author":"Sun","year":"2024","journal-title":"Ec-dit: Scaling diffusion transformers with adaptive expert-choice routing"},{"key":"ref65","author":"Tang","year":"2024","journal-title":"Mambamim: Pre-training mamba with state space token-interpolation"},{"key":"ref66","article-title":"Generative modeling with explicit memory","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","volume-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024"},{"key":"ref68","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref69","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01522"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref72","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Exploring token pruning in vision state space models","author":"Zhan","year":"2024","journal-title":"NeurIPS"},{"key":"ref74","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017","journal-title":"In ICLR"},{"key":"ref75","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2024","journal-title":"TMLR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00806"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445760.pdf?arnumber=11445760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:50Z","timestamp":1777529750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01457","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}